Skip to content

Fix typo in vision argument of Ollama #1811

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
RobinPicard merged 1 commit into from
Jan 20, 2026
Merged

Fix typo in vision argument of Ollama #1811

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
4 changes: 3 additions & 1 deletion outlines/models/ollama.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -96,7 +96,7 @@ def _create_message(self, role: str, content: str | list) -> dict:
return {
"role": role,
"content": prompt,
"image": [image.image_str for image in images],
"images": [image.image_str for image in images],
}

else:
Expand Down Expand Up @@ -193,6 +193,8 @@ def generate(self,
if "model" not in kwargs and self.model_name is not None:
kwargs["model"] = self.model_name

print(self.type_adapter.format_input(model_input))

response = self.client.chat(
messages=self.type_adapter.format_input(model_input),
format=self.type_adapter.format_output_type(output_type),
Expand Down
4 changes: 2 additions & 2 deletions tests/models/test_ollama_type_adapter.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -68,7 +68,7 @@ def test_ollama_type_adapter_input_vision(adapter, image):
assert result[0] == {
"role": "user",
"content": text_input,
"image": [image_input.image_str],
"images": [image_input.image_str],
}


Expand All @@ -86,7 +86,7 @@ def test_ollama_type_adapter_input_chat(adapter, image):
assert isinstance(result, list)
assert len(result) == 3
assert result[0] == {"role": "system", "content": "prompt"}
assert result[1] == {"role": "user", "content": "hello", "image": [image_input.image_str]}
assert result[1] == {"role": "user", "content": "hello", "images": [image_input.image_str]}
assert result[2] == {"role": "assistant", "content": "response"}


Expand Down
Loading